macros.xml

<?xml version="1.0"?>
<macros>
    <xml name="requirements">
        <requirements>
            <requirement type="package" version="@TOOL_VERSION@">obitools4</requirement>
        </requirements>
    </xml>

    <token name="@TOOL_VERSION@">4.4.41</token>
    <token name="@VERSION_SUFFIX@">0</token>
    <token name="@PROFILE@">25.1</token>

    <xml name="stdio">
        <stdio>
            <exit_code range="1:" level="fatal" description="Error in Obitools execution" />           
        </stdio>
    </xml>

    <token name="@INPUT_FORMATS@">fastqsanger,fastqsanger.gz,fastqsolexa,fastqsolexa.gz,fasta,fasta.gz</token>
    
    <token name="@OPTIONS_OBIGREP@"><![CDATA[
            #if str($i.options_grep.options_grep_selector) == 'sequence'
                -s '${i.options_grep.sequence}'
            #elif str($i.options_grep.options_grep_selector) == 'definition'
                -D '${i.options_grep.definition}'
            #elif str($i.options_grep.options_grep_selector) == 'identifier'
                -I '${i.options_grep.identifier}'
            #elif str($i.options_grep.options_grep_selector) == 'idlist'
                --id-list ${i.options_grep.idlist}
            #elif str($i.options_grep.options_grep_selector) == 'attribute' and str($i.options_grep.attrib_value)
                -a ${i.options_grep.attribute}=${i.options_grep.attrib_value}
            #elif str($i.options_grep.options_grep_selector) == 'attribute'
                -A ${i.options_grep.attribute}
            #elif str($i.options_grep.options_grep_selector) == 'predicat'
                -p '${i.options_grep.predicat}'
            #elif str($i.options_grep.options_grep_selector) == 'lmax'
                -L ${i.options_grep.lmax}
            #elif str($i.options_grep.options_grep_selector) == 'lmin'
                -l ${i.options_grep.lmin}
            #elif str($i.options_grep.options_grep_selector) == 'maxcount'
                -C ${i.options_grep.maxcount}
            #elif str($i.options_grep.options_grep_selector) == 'mincount'
                -c ${i.options_grep.mincount}
            #end if
    ]]></token>

    <xml name="taxo_macro_optional">
        <conditional name="taxo_condi">
            <param name="taxonomic_select" type="select" display="radio" label="Do you want to use a taxonomic database ?">
                <option value="no_taxo">No Taxonomic Database</option>
                <option value="use_taxo">Use taxonomic Database</option>
            </param>
            <when value="no_taxo"></when>
            <when value="use_taxo">
                <conditional name="taxonomy">
                    <param name="taxonomy_source" type="select" label="Choose source of NCBI Taxonomy">
                        <option value="cached" selected="true">Use built-in NCBI Taxonomy database</option>
                        <option value="history">Datasets from history</option>
                    </param>
                        <when value="cached">
                            <param type="select" name="taxonomy_table" label="NCBI Taxonomy database">
                                <options from_data_table="ncbi_taxonomy">
                                    <filter type="sort_by" column="name"/>
                                    <validator type="no_options" message="No NCBI Taxonomy downloads are available"/>
                                </options>
                                <validator type="no_options" message="No NCBI Taxonomy database download is available"/>
                            </param>
                        </when>
                        <when value="history">
                            <param name="taxdump" type="data" format="tar,tar.gz,tgz,csv" label="NCBI Taxonomic database"/>
                        </when>
                </conditional>
            </when>
        </conditional>
    </xml>

    <xml name="taxo_macro">
        <conditional name="taxonomy">
            <param name="taxonomy_source" type="select" label="Choose source of NCBI Taxonomy">
                <option value="cached" selected="true">Use built-in NCBI Taxonomy database</option>
                <option value="history">Datasets from history</option>
            </param>
            <when value="cached">
                <param type="select" name="taxonomy_table" label="NCBI Taxonomy database">
                    <options from_data_table="ncbi_taxonomy">
                        <filter type="sort_by" column="name"/>
                        <validator type="no_options" message="No NCBI Taxonomy downloads are available"/>
                    </options>
                    <validator type="no_options" message="No NCBI Taxonomy database download is available"/>
                </param>
            </when>
            <when value="history">
                <param name="taxdump" type="data" format="tar,tar.gz,tgz,csv" label="NCBI Taxonomic database"/>
            </when>
        </conditional>
    </xml>

    <token name="@TAXO_DIR@"><![CDATA[
        #if str($taxonomy.taxonomy_source) == 'cached':
            --taxonomy '$taxonomy.taxonomy_table.fields.path'
        #else
            --taxonomy '$taxonomy.taxdump'
        #end if
    ]]></token>

    <token name="@TAXO_DIR_OPTIONAL@"><![CDATA[
        #if str($taxo_condi.taxonomic_select) == 'use_taxo':
            #if str($taxo_condi.taxonomy.taxonomy_source) == 'cached':
                --taxonomy '$taxonomy.taxonomy_table.fields.path'
            #else
                --taxonomy '$taxo_condi.taxonomy.taxdump'
            #end if
        #end if
    ]]></token>

    <token name="@OUT_FORMAT@"><![CDATA[
        #if str($out_format) in ["fasta.gz", "fastq.gz"] or ($input.ext.endswith(".gz") and str($out_format) not in ["fasta", "fastq"])
            --compress
        #end if
        #if str($out_format) in ["fasta", "fasta.gz"]
            --fasta-output
        #elif str($out_format) in ["fastq", "fastq.gz"]
            --fastq-output
        #end if
    ]]></token>
    
    <xml name="out_format_macro">
        <param name="out_format" type="select" optional="true" label="Output data type" help="For FASTA/Q the the default output type is the same as the input type, if you want to decompress the output, select the non compressed version of your format">
            <option value="fasta">fasta</option>
            <option value="fasta.gz">fasta.gz</option>
            <option value="fastq">fastq</option>
            <option value="fastq.gz">fastq.gz</option>
        </param>
    </xml>

    <xml name="change_format_macro">
        <change_format>
                <when input="out_format" value="fasta" format="fasta"/>
                <when input="out_format" value="fastq" format="fastq"/>
                <when input="out_format" value="fasta.gz" format="fasta.gz"/>
                <when input="out_format" value="fastq.gz" format="fastq.gz"/>
        </change_format>
    </xml>

    <xml name="compress_bool_macro">
        <param name="compress_bool" type="boolean" truevalue="--compress" falsevalue="" checked="false" label="Do you want to compress the output file ?"/>
    </xml>

        <xml name="macro_restrict_rank">
        <param name="rank" type="select" label="Restrict to the given taxonomic rank" multiple="true" optional="true">
            <option value="species">species</option>
            <option value="genus">genus</option>
            <option value="family">family</option>
            <option value="class">class</option>
            <option value="order">order</option>
            <option value="phylum">phylum</option>
            <option value="kingdom">kingdom</option>
            <option value="domain">domain</option>
        </param>
    </xml>

    <token name="@RESTRICT_TO_RANK@"><![CDATA[
        #for i in $rank
            --require-rank $i
        #end for
    ]]></token>

    <xml name="macro_restrict_taxon">
        <param name="taxon" type="integer" label="Restrict to a specific taxon by his taxid" help="Require that the actual taxon of the sequence belongs the provided taxid." optional="true"/>
    </xml>

    <token name="@RESTRICT_TO_TAXON@"><![CDATA[
        #if $taxon
            --restrict-to-taxon $taxon
        #end if
    ]]></token>

    <token name="@OBITOOLS_LINK_OBI4@">
<![CDATA[
--------

**Project links:**

`OBITools`_

.. _OBITools: https://obitools4.metabarcoding.org/
]]>
    </token>
    <xml name="option_grep_macro">
        <conditional name="options_grep">
            <param name="options_grep_selector" type="select" label="Choose the sequence record selection option">
                <option value="sequence" selected="true">sequence</option>
                <option value="definition">definition</option>
                <option value="identifier">identifier</option>
                <option value="idlist">idlist</option>
                <option value="attribute">attribute</option>
                <option value="predicat">predicat</option>
                <option value="lmax">lmax</option>
                <option value="lmin">lmin</option>
                <option value="maxcount">maxcount</option>
                <option value="mincount">mincount</option>
            </param>
            <when value="sequence">
                <param name="sequence" type="text" label="Regular expression pattern to be tested against the sequence itself. The pattern is case insensitive." optional="false">
                    <expand macro="sanitizer"/>
                </param>
            </when>
            <when value="definition">
                <param name="definition" type="text" label="Regular expression pattern to be tested against the definition of the sequence record. The pattern is case sensitive." optional="false">
                    <expand macro="sanitizer"/>
                </param>
            </when>
            <when value="identifier">
                <param name="identifier" type="text" label="Regular expression pattern to be tested against the identifier of the sequence record. The pattern is case sensitive." optional="false">
                    <expand macro="sanitizer"/>
                </param>
            </when>
            <when value="idlist">
                <param name="idlist" type="data" format="txt,tabular" label="points to a text file containing the list of sequence record identifiers to be selected. The file format consists in a single identifier per line." optional="false"/>
            </when>
            <when value="attribute">
                <param name="attribute" type="select" label="Attribute to use as key in key=value." help="Filters sequences that contain the attribute, or match a specific key=value if a value is provided." optional="false">
                    <expand macro="attributes"/>
                </param>
                <param name="attrib_value" type="text" label="Value to filter on in key=value" help="Supports substring and regular expression matches." optional="true">
                    <expand macro="sanitizer"/>
                    <option value="12S">12S</option>
                    <option value="16S">16S</option>
                    <option value="18S">18S</option>
                    <option value="28S">28S</option>
                    <option value="COI">COI</option>
                    <option value="COII">COII</option>
                    <option value="COXIII">COXIII</option>
                    <option value="CYTB">Cytb</option>
                    <option value="H3">H3</option>
                    <option value="ND1">ND1</option>
                    <option value="ND2">ND2</option>
                    <option value="ND3">ND3</option>
                    <option value="ND4">ND4</option>
                    <option value="ND4L">ND4L</option>
                    <option value="ND5-0">ND5-0</option>
                    <option value="ND6">ND6</option>
                    <option value="rbcl">rbcl</option> 
                </param>
            </when>
            <when value="predicat">
                <param name="predicat" type="text" optional="false" label="Python boolean expression to be evaluated for each sequence record. The attribute keys defined for each sequence record can be used in the expression as variable names. An extra variable named 'sequence' refers to the sequence record itself. ex: annotations.mode!='join' if you want to keep only the sequences that don't have the mode:join on the annotation line">
                    <expand macro="sanitizer"/>
                </param>
            </when>
            <when value="lmax">
                <param name="lmax" type="integer" label="lmax" optional="false" help="Keeps sequence records whose sequence length is equal or shorter than lmax"/>
            </when>
            <when value="lmin">
                <param name="lmin" type="integer" label="lmin" optional="false" help="Keeps sequence records whose sequence length is equal or longer than lmin"/>
            </when>
            <when value="maxcount">
                <param name="maxcount" type="integer" label="maxcount" optional="false" help="Keeps sequence records whose sequence count is equal or shorter than maxcount"/>
            </when>
            <when value="mincount">
                <param name="mincount" type="integer" label="mincount" optional="false" help="Keeps sequence records whose sequence count is equal or longer than mincount"/>
            </when>
        </conditional>
    </xml>
    <xml name="attributes">
        <option value="ali_dir" selected="true">ali_dir</option>
        <option value="ali_length">ali_length</option>
        <option value="avg_quality">avg_quality</option>
        <option value="best_match">best_match</option>
        <option value="best_identity">best_identity</option>
        <option value="chimera">chimera</option>
        <option value="class">class</option>
        <option value="cluster">cluster</option>
        <option value="complemented">complemented</option>
        <option value="count">count</option>
        <option value="cut">cut</option>
        <option value="direction">direction</option>
        <option value="distance">distance</option>
        <option value="error">error</option>
        <option value="experiment">experiment</option>
        <option value="family">family</option>
        <option value="family_name">family_name</option>
        <option value="forward_error">forward_error</option>
        <option value="forward_match">forward_match</option>
        <option value="forward_primer">forward_primer</option>
        <option value="forward_score">forward_score</option>
        <option value="forward_tag">forward_tag</option>
        <option value="forward_tm">forward_tm</option>
        <option value="genus">genus</option>
        <option value="genus_name">genus_name</option>
        <option value="head_quality">head_quality</option>
        <option value="id_status">id_status</option>
        <option value="merged_star">merged_star</option>
        <option value="merged_sample">merged_sample</option>
        <option value="mid_quality">mid_quality</option>
        <option value="mode">mode</option>
        <option value="obiclean_cluster">obiclean_cluster</option>
        <option value="obiclean_count">obiclean_count</option>
        <option value="obiclean_head">obiclean_head</option>
        <option value="obiclean_headcount">obiclean_headcount</option>
        <option value="obiclean_internalcount">obiclean_internalcount</option>
        <option value="obiclean_samplecount">obiclean_samplecount</option>
        <option value="obiclean_singletoncount">obiclean_singletoncount</option>
        <option value="obiclean_status">obiclean_status</option>
        <option value="obimultiplex_amplicon_rank">obimultiplex_amplicon_rank</option>
        <option value="obimultiplex_forward_matching">obimultiplex_forward_matching</option>
        <option value="obimultiplex_forward_primer">obimultiplex_forward_primer</option>
        <option value="obimultiplex_forward_tag_dist">obimultiplex_forward_tag_dist</option>
        <option value="obimultiplex_reverse_matching">obimultiplex_reverse_matching</option>
        <option value="obimultiplex_reverse_primer">obimultiplex_reverse_primer</option>
        <option value="obimultiplex_reverse_tag_dist">obimultiplex_reverse_tag_dist</option>
        <option value="occurrence">occurrence</option>
        <option value="order">order</option>
        <option value="order_name">order_name</option>
        <option value="pairend_limit ">pairend_limit </option>
        <option value="pairing_fast_count">pairing_fast_count</option>
        <option value="pairing_fast_overlap">pairing_fast_overlap</option>
        <option value="pairing_fast_score">pairing_fast_score</option>
        <option value="partial ">partial </option>
        <option value="rank">rank</option>
        <option value="reverse_error">reverse_error</option>
        <option value="reverse_match">reverse_match</option>
        <option value="reverse_primer">reverse_primer</option>
        <option value="reverse_score">reverse_score</option>
        <option value="reverse_tag">reverse_tag</option>
        <option value="reverse_tm">reverse_tm</option>
        <option value="sample">sample</option>
        <option value="scientific_name">scientific_name</option>
        <option value="score">score</option>
        <option value="score_norm">score_norm</option>
        <option value="select">select</option>
        <option value="seq_ab_match">seq_ab_match</option>
        <option value="seq_a_single">seq_a_single</option>
        <option value="seq_a_mismatch">seq_a_mismatch</option>
        <option value="seq_a_deletion">seq_a_deletion</option>
        <option value="seq_a_insertion">seq_a_insertion</option>
        <option value="seq_b_single">seq_b_single</option>
        <option value="seq_b_mismatch">seq_b_mismatch</option>
        <option value="seq_b_deletion">seq_b_deletion</option>
        <option value="seq_b_insertion">seq_b_insertion</option>
        <option value="seq_length">seq_length</option>
        <option value="seq_length_ori">seq_length_ori</option>
        <option value="seq_rank">seq_rank</option>
        <option value="sminL">sminL</option>
        <option value="sminR">sminR</option>
        <option value="species">species</option>
        <option value="species_list">species_list</option>
        <option value="species_name">species_name</option>
        <option value="status">status</option>
        <option value="strand">strand</option>
        <option value="tail_quality">tail_quality</option>
        <option value="taxid">taxid</option>
    </xml>
  
    <xml name="input_format_options_macro">
        <section name="input_format_options" title="Input format options" expanded="false">
            <param name="options_inputtype" type="select"  optional="true" label="Specify the input datatype" help="default: determine automatically (should only be necessary for non FASTA/FASTQ datasets)">
                <option value="--genbank">genbank</option>
                <option value="--embl">embl</option>
                <option value="--solexa">solexa</option>
                <option value="--ecopcr">ecopcr</option>
                <option value="--ecopcrdb">ecopcrdb</option>
                <option value="--fasta">fasta (including obitools fasta extentions)</option>
            </param>
        </section>
    </xml>

    <token name="@INPUT_FORMAT@"><![CDATA[
        #if $input_format_options.options_inputtype
            $input_format_options.options_inputtype
        #else
            #if $input.ext.startswith("fasta")
                --fasta
            #else if $input.ext.startswith("fastqsolexa")
                ## input file is in fastq nucleic format produced by solexa sequencer
                --solexa
            #end if
        #end if
    ]]></token>

    <xml name="sanitizer">
        <sanitizer>
            <valid initial="default">
                <add value="&quot;"/>
                <add value="["/>
                <add value="]"/>
                <add value="{"/> 
                <add value="}"/>  
            </valid>
            <mapping initial="default">
                <add source="&gt;" target="\&gt;"/>
            </mapping>
        </sanitizer>
    </xml>

    <xml name="citation">
        <citations>
            <citation type="doi">10.1111/1755-0998.12428</citation>
        </citations>
    </xml>

</macros>